© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125952
    Prev
    Next
    INDEX
    Explanations

    error handling and exception-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è²
    -0.07
    ccione
    -0.07
    ande
    -0.07
    主任
    -0.07
    ÑıÑĩ
    -0.07
    lane
    -0.07
    uai
    -0.07
    lobber
    -0.06
    parable
    -0.06
    ervo
    -0.06
    POSITIVE LOGITS
    åĭ¢
    0.06
    owo
    0.06
    çīĽ
    0.06
    esse
    0.05
     Zucker
    0.05
    ëĵĿ
    0.05
    VILLE
    0.05
    ãģĤ
    0.05
     consequence
    0.05
    OMP
    0.05
    Activations Density 0.001%

    No Known Activations